Where does the sparsity in image signals come from? Local and nonlocal image models have supplied complementary views toward the regularity in natural images the former attempts t...
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...
In this paper we reformulate the 3D reconstruction of deformable surfaces from monocular video sequences as a labeling problem. We solve simultaneously for the assignment of featu...
Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear...
—Image-based computation of a 3D map for an indoor environment is a very challenging task, but also a useful step for vision-based navigation and path planning for autonomous sys...